The major goal of the project is to provide computational resources to the FunMat-II competence center. Our scientific goal is to establish a hybrid platform of high accuracy quantum mechanical calculations and active machine learning of big data. We primarily focus on nitride materials, which includes high-energy density materials and materials with extraordinary hardness. The approach is to use ab-initio molecular dynamics simulations or static density functonal theory calculations (VASP, QE) to control classical molecular dynamics simulations (LAMMPS). The connection is established by machine learning the interatomic potentials (MLIP). By utilizing the gained speed up in the computations we will be able to i) calculate high-temperature phase diagrams and elasticity, ii) capture rare diffusion effects, iii) predict thermal conductivity of hard coatings, iv) explore the broadening of Fermi surface in high-energy density semimetals, etc. Through the FunMat-II competence center we are in close collaboration with Seco Tools and Sandik Coromant. This industrial segment has major interest in high temperature elastic and mechanical properties of nitride alloys. We also collaborate world-leading experimentalists in the filed of high-pressure physics. Our research is supported by the Swedish strategic FunMat-II consortium, Vinnova (Diarienr: 2017-04943), Vinnova (Diarienr: 2018-04297) and the Interdisciplinary Laboratory for Advanced Functional Materials at Linköping University. The quantum mechanical (electronic and phonon) calculations will be performed using VASP and Quantum Espresso (QE). The classical molecular dynamics simulations will be done using LAMMPS.